Similarity-Based Self-Construct Graph Model for Predicting Patient Criticalness Using Graph Neural Networks and EHR Data

2025/08/01 by Mukesh Sahu, Sahu, Mukesh Kumar, Pinki Roy +1
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Healthcare #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2508.00615

openalex publication_date 2025/08/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Accurately predicting the criticalness of ICU patients (such as in-ICU mortality risk) is vital for early intervention in critical care. However, conventional models often treat each patient in isolation and struggle to exploit the relational structure in Electronic Health Records (EHR). We propose a Similarity-Based Self-Construct Graph Model (SBSCGM) that dynamically builds a patient similarity graph from multi-modal EHR data, and a HybridGraphMedGNN architecture that operates on this graph to predict patient mortality and a continuous criticalness score. SBSCGM uses a hybrid similarity measure (combining feature-based and structural similarities) to connect patients with analogous clinical profiles in real-time. The HybridGraphMedGNN integrates Graph Convolutional Network (GCN), GraphSAGE, and Graph Attention Network (GAT) layers to learn robust patient representations, leveraging both local and global graph patterns. In experiments on 6,000 ICU stays from the MIMIC-III dataset, our model achieves state-of-the-art performance (AUC-ROC 0.94) outperforming baseline classifiers and single-type GNN models. We also demonstrate improved precision/recall and show that the attention mechanism provides interpretable insights into model predictions. Our framework offers a scalable and interpretable solution for critical care risk prediction, with potential to support clinicians in real-world ICU deployment.

Citations

• Graph Neural Networks for Heart Failure Prediction on an EHR-Based Patient Similarity Graph
• Leveraging graph neural networks for supporting Automatic Triage of Patients
• Hypergraph Convolutional Networks for Fine-grained ICU Patient Similarity Analysis and Risk Prediction
• Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction
• Scalable and accurate deep learning with electronic health records
• Graph Attention Networks
• Inductive Representation Learning on Large Graphs
• Semi-Supervised Classification with Graph Convolutional Networks
• RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism

Related

• Graph Neural Networks for Heart Failure Prediction on an EHR-Based Patient Similarity Graph
• Hypergraph Convolutional Networks for Fine-grained ICU Patient Similarity Analysis and Risk Prediction
• Predicting Patient Outcomes with Graph Representation Learning
• Sepsis Prediction Using Graph Convolutional Networks over Patient-Feature-Value Triplets
• Bridging Graph and State-Space Modeling for Intensive Care Unit Length of Stay Prediction